arXiv:2606. 22030v2 Announce Type: replace Abstract: We investigate when belief-based memory actually improves large language model (LLM) agents.
arXiv:2608.21230v1 Announce Type: cross Abstract: Persistent memory makes false information durable: once a false statement is stored, it can be retrieved into future sessions that match it. We measu...
The paper introduces CAPTURE, a system designed to help personalized language agents distinguish genuine preference changes from temporary context shifts or malicious memory poisoning. CAPTURE employs a neural differential-equation belief tracker, a multi-timescale memory ledger, uncertainty-triggered clarification, and counterfactual auditing to resolve ambiguity. Experiments on 480 episodes from 96 users show CAPTURE outperforms baseline methods, limiting poisoning success while accepting most real preference updates.
UTILMEM is a new diagnostic benchmark that tests how conversational agents use long‑term memory, focusing on reasoning over dense histories, spotting implicitly relevant memories, synthesizing distributed evidence, and resisting interference from similar distractors. It contains 1,717 instances across five domains and evaluates a range of retrieval‑based and memory‑augmented systems. The study shows that strong performance on traditional factual recall does not guarantee effective memory utilization, highlighting a gap between retrieving information and integrating it into coherent, task‑oriented outputs.
Agent Zero Memory is a provenance‑aware long‑term memory system for large language model agents that distills user interactions into three parallel memory structures: an episodic timeline, an associative entity‑event knowledge graph, and a semantic, citation‑locked hierarchical documentary memory. Retrieval is performed via an intent gate, source router, and concurrent searches across the three systems, producing integrated, cited answers that exclude fabrication and require evidence the reader has opened. The system achieves state‑of‑the‑art performance on LongMemEval (95.60%) and LoCoMo (93.60%) while offering a favorable accuracy‑cost‑latency trade‑off across multiple backbone LLMs.
arXiv:2607. 16716v1 Announce Type: new Abstract: Large language models and LLM-based agents are widely used as personal chat assistants, enterprise copilots, and autonomous workflow agents.
Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent evidence and combine them through voting or weighting.
The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.
Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context. While this has improved the agent's functionality and continuity across tasks, it has also introduced a new attack surface: the agent's own reasoning history.
arXiv:2608. 19701v1 Announce Type: new Abstract: Long-term multi-agent systems continuously accumulate the memories produced by different agents.
arXiv:2607. 05029v1 Announce Type: cross Abstract: Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context.
The paper introduces FAME, a training‑free framework that evaluates false memory in autonomous agents by tracking how their internal beliefs shift under counterfactual scenarios. False memory, defined as biases arising from spurious correlations, environment shifts, or knowledge conflicts, is hard to detect with standard methods. FAME measures concept drift in hidden states, achieving AUROCs between 76.2% and 96.7% and outperforming baselines on benchmarks such as GSM‑Symbolic, GitChameleon, and BigBench‑Hard.
arXiv:2608. 10676v1 Announce Type: new Abstract: Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments.